Matthews Correlation Coefficient Loss for Deep Convolutional Networks: Application to Skin Lesion Segmentation

TL;DR

This paper introduces a novel loss function based on the Matthews correlation coefficient for deep learning skin lesion segmentation, effectively addressing class imbalance and improving segmentation accuracy over traditional Dice loss.

Contribution

The paper proposes a new MCC-based loss function for deep segmentation models, specifically targeting class imbalance issues in skin lesion datasets.

Findings

MCC loss outperforms Dice loss in skin lesion segmentation.

Models trained with MCC loss show up to 11.25% improvement in Jaccard index.

The approach is validated on three different skin lesion datasets.

Abstract

The segmentation of skin lesions is a crucial task in clinical decision support systems for the computer aided diagnosis of skin lesions. Although deep learning-based approaches have improved segmentation performance, these models are often susceptible to class imbalance in the data, particularly, the fraction of the image occupied by the background healthy skin. Despite variations of the popular Dice loss function being proposed to tackle the class imbalance problem, the Dice loss formulation does not penalize misclassifications of the background pixels. We propose a novel metric-based loss function using the Matthews correlation coefficient, a metric that has been shown to be efficient in scenarios with skewed class distributions, and use it to optimize deep segmentation models. Evaluations on three skin lesion image datasets: the ISBI ISIC 2017 Skin Lesion Segmentation Challenge dataset, the DermoFit Image Library, and the PH2 dataset, show that models trained using the proposed loss function outperform those trained using Dice loss by 11.25%, 4.87%, and 0.76% respectively in the mean Jaccard index. The code is available at https://github.com/kakumarabhishek/MCC-Loss.